#include "config.h"
+#include <stdlib.h>
#include <stddef.h>
#include <string.h>
#include <locale.h>
#include "glib.h"
#include "gunichartables.h"
#include "gmirroringtable.h"
+#include "gscripttable.h"
#include "gunicodeprivate.h"
#include "galias.h"
-#define ISDIGIT(Type) IS ((Type), \
- OR (G_UNICODE_DECIMAL_NUMBER, \
- OR (G_UNICODE_LETTER_NUMBER, \
- OR (G_UNICODE_OTHER_NUMBER, 0))))
-
#define ISALPHA(Type) IS ((Type), \
OR (G_UNICODE_LOWERCASE_LETTER, \
OR (G_UNICODE_UPPERCASE_LETTER, \
OR (G_UNICODE_COMBINING_MARK, \
OR (G_UNICODE_ENCLOSING_MARK, 0))))
+#define ISZEROWIDTHTYPE(Type) IS ((Type), \
+ OR (G_UNICODE_NON_SPACING_MARK, \
+ OR (G_UNICODE_ENCLOSING_MARK, \
+ OR (G_UNICODE_FORMAT, 0))))
+
/**
* g_unichar_isalnum:
* @c: a Unicode character
unsigned int i;
for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
if (title_table[i][0] == c)
- return 1;
- return 0;
+ return TRUE;
+ return FALSE;
}
/**
{
return ((c >= 'a' && c <= 'f')
|| (c >= 'A' && c <= 'F')
- || ISDIGIT (TYPE (c)));
+ || (TYPE (c) == G_UNICODE_DECIMAL_NUMBER));
}
/**
}
/**
+ * g_unichar_iszerowidth:
+ * @c: a Unicode character
+ *
+ * Determines if a given character typically takes zero width when rendered.
+ * The return value is %TRUE for all non-spacing and enclosing marks
+ * (e.g., combining accents), format characters, zero-width
+ * space, but not U+00AD SOFT HYPHEN.
+ *
+ * A typical use of this function is with one of g_unichar_iswide() or
+ * g_unichar_iswide_cjk() to determine the number of cells a string occupies
+ * when displayed on a grid display (terminals). However, note that not all
+ * terminals support zero-width rendering of zero-width marks.
+ *
+ * Return value: %TRUE if the character has zero width
+ *
+ * Since: 2.14
+ **/
+gboolean
+g_unichar_iszerowidth (gunichar c)
+{
+ if (G_UNLIKELY (c == 0x00AD))
+ return FALSE;
+
+ if (G_UNLIKELY (ISZEROWIDTHTYPE (TYPE (c))))
+ return TRUE;
+
+ if (G_UNLIKELY ((c >= 0x1160 && c < 0x1200) ||
+ c == 0x200B))
+ return TRUE;
+
+ return FALSE;
+}
+
+/**
* g_unichar_iswide:
* @c: a Unicode character
*
|| (c >= 0x30000 && c <= 0x3fffd));
}
+
+struct Interval
+{
+ gunichar start, end;
+};
+
+static int
+interval_compare (const void *key, const void *elt)
+{
+ gunichar c = GPOINTER_TO_UINT (key);
+ struct Interval *interval = (struct Interval *)elt;
+
+ if (c < interval->start)
+ return -1;
+ if (c > interval->end)
+ return +1;
+
+ return 0;
+}
+
+/**
+ * g_unichar_iswide_cjk:
+ * @c: a Unicode character
+ *
+ * Determines if a character is typically rendered in a double-width
+ * cell under legacy East Asian locales. If a character is wide according to
+ * g_unichar_iswide(), then it is also reported wide with this function, but
+ * the converse is not necessarily true. See the
+ * <ulink url="http://www.unicode.org/reports/tr11/">Unicode Standard
+ * Annex #11</ulink> for details.
+ *
+ * Return value: %TRUE if the character is wide in legacy East Asian locales
+ *
+ * Since: 2.12
+ */
+/* This function stolen from Markus Kuhn <Markus.Kuhn@cl.cam.ac.uk>. */
+gboolean
+g_unichar_iswide_cjk (gunichar c)
+{
+ /* sorted list of non-overlapping intervals of East Asian Ambiguous
+ * characters, generated by "uniset +WIDTH-A -cat=Me -cat=Mn -cat=Cf c" */
+ static const struct Interval ambiguous[] = {
+ { 0x00A1, 0x00A1 }, { 0x00A4, 0x00A4 }, { 0x00A7, 0x00A8 },
+ { 0x00AA, 0x00AA }, { 0x00AE, 0x00AE }, { 0x00B0, 0x00B4 },
+ { 0x00B6, 0x00BA }, { 0x00BC, 0x00BF }, { 0x00C6, 0x00C6 },
+ { 0x00D0, 0x00D0 }, { 0x00D7, 0x00D8 }, { 0x00DE, 0x00E1 },
+ { 0x00E6, 0x00E6 }, { 0x00E8, 0x00EA }, { 0x00EC, 0x00ED },
+ { 0x00F0, 0x00F0 }, { 0x00F2, 0x00F3 }, { 0x00F7, 0x00FA },
+ { 0x00FC, 0x00FC }, { 0x00FE, 0x00FE }, { 0x0101, 0x0101 },
+ { 0x0111, 0x0111 }, { 0x0113, 0x0113 }, { 0x011B, 0x011B },
+ { 0x0126, 0x0127 }, { 0x012B, 0x012B }, { 0x0131, 0x0133 },
+ { 0x0138, 0x0138 }, { 0x013F, 0x0142 }, { 0x0144, 0x0144 },
+ { 0x0148, 0x014B }, { 0x014D, 0x014D }, { 0x0152, 0x0153 },
+ { 0x0166, 0x0167 }, { 0x016B, 0x016B }, { 0x01CE, 0x01CE },
+ { 0x01D0, 0x01D0 }, { 0x01D2, 0x01D2 }, { 0x01D4, 0x01D4 },
+ { 0x01D6, 0x01D6 }, { 0x01D8, 0x01D8 }, { 0x01DA, 0x01DA },
+ { 0x01DC, 0x01DC }, { 0x0251, 0x0251 }, { 0x0261, 0x0261 },
+ { 0x02C4, 0x02C4 }, { 0x02C7, 0x02C7 }, { 0x02C9, 0x02CB },
+ { 0x02CD, 0x02CD }, { 0x02D0, 0x02D0 }, { 0x02D8, 0x02DB },
+ { 0x02DD, 0x02DD }, { 0x02DF, 0x02DF }, { 0x0391, 0x03A1 },
+ { 0x03A3, 0x03A9 }, { 0x03B1, 0x03C1 }, { 0x03C3, 0x03C9 },
+ { 0x0401, 0x0401 }, { 0x0410, 0x044F }, { 0x0451, 0x0451 },
+ { 0x2010, 0x2010 }, { 0x2013, 0x2016 }, { 0x2018, 0x2019 },
+ { 0x201C, 0x201D }, { 0x2020, 0x2022 }, { 0x2024, 0x2027 },
+ { 0x2030, 0x2030 }, { 0x2032, 0x2033 }, { 0x2035, 0x2035 },
+ { 0x203B, 0x203B }, { 0x203E, 0x203E }, { 0x2074, 0x2074 },
+ { 0x207F, 0x207F }, { 0x2081, 0x2084 }, { 0x20AC, 0x20AC },
+ { 0x2103, 0x2103 }, { 0x2105, 0x2105 }, { 0x2109, 0x2109 },
+ { 0x2113, 0x2113 }, { 0x2116, 0x2116 }, { 0x2121, 0x2122 },
+ { 0x2126, 0x2126 }, { 0x212B, 0x212B }, { 0x2153, 0x2154 },
+ { 0x215B, 0x215E }, { 0x2160, 0x216B }, { 0x2170, 0x2179 },
+ { 0x2190, 0x2199 }, { 0x21B8, 0x21B9 }, { 0x21D2, 0x21D2 },
+ { 0x21D4, 0x21D4 }, { 0x21E7, 0x21E7 }, { 0x2200, 0x2200 },
+ { 0x2202, 0x2203 }, { 0x2207, 0x2208 }, { 0x220B, 0x220B },
+ { 0x220F, 0x220F }, { 0x2211, 0x2211 }, { 0x2215, 0x2215 },
+ { 0x221A, 0x221A }, { 0x221D, 0x2220 }, { 0x2223, 0x2223 },
+ { 0x2225, 0x2225 }, { 0x2227, 0x222C }, { 0x222E, 0x222E },
+ { 0x2234, 0x2237 }, { 0x223C, 0x223D }, { 0x2248, 0x2248 },
+ { 0x224C, 0x224C }, { 0x2252, 0x2252 }, { 0x2260, 0x2261 },
+ { 0x2264, 0x2267 }, { 0x226A, 0x226B }, { 0x226E, 0x226F },
+ { 0x2282, 0x2283 }, { 0x2286, 0x2287 }, { 0x2295, 0x2295 },
+ { 0x2299, 0x2299 }, { 0x22A5, 0x22A5 }, { 0x22BF, 0x22BF },
+ { 0x2312, 0x2312 }, { 0x2460, 0x24E9 }, { 0x24EB, 0x254B },
+ { 0x2550, 0x2573 }, { 0x2580, 0x258F }, { 0x2592, 0x2595 },
+ { 0x25A0, 0x25A1 }, { 0x25A3, 0x25A9 }, { 0x25B2, 0x25B3 },
+ { 0x25B6, 0x25B7 }, { 0x25BC, 0x25BD }, { 0x25C0, 0x25C1 },
+ { 0x25C6, 0x25C8 }, { 0x25CB, 0x25CB }, { 0x25CE, 0x25D1 },
+ { 0x25E2, 0x25E5 }, { 0x25EF, 0x25EF }, { 0x2605, 0x2606 },
+ { 0x2609, 0x2609 }, { 0x260E, 0x260F }, { 0x2614, 0x2615 },
+ { 0x261C, 0x261C }, { 0x261E, 0x261E }, { 0x2640, 0x2640 },
+ { 0x2642, 0x2642 }, { 0x2660, 0x2661 }, { 0x2663, 0x2665 },
+ { 0x2667, 0x266A }, { 0x266C, 0x266D }, { 0x266F, 0x266F },
+ { 0x273D, 0x273D }, { 0x2776, 0x277F }, { 0xE000, 0xF8FF },
+ { 0xFFFD, 0xFFFD }, { 0xF0000, 0xFFFFD }, { 0x100000, 0x10FFFD }
+ };
+
+ if (g_unichar_iswide (c))
+ return TRUE;
+
+ if (bsearch (GUINT_TO_POINTER (c), ambiguous, G_N_ELEMENTS (ambiguous), sizeof ambiguous[0],
+ interval_compare))
+ return TRUE;
+
+ return FALSE;
+}
+
+
/**
* g_unichar_toupper:
* @c: a Unicode character
return g_utf8_get_char (p);
}
else
- return val ? val : c;
+ {
+ /* Some lowercase letters, e.g., U+000AA, FEMININE ORDINAL INDICATOR,
+ * do not have an uppercase equivalent, in which case val will be
+ * zero. */
+ return val ? val : c;
+ }
}
else if (t == G_UNICODE_TITLECASE_LETTER)
{
return g_utf8_get_char (p);
}
else
- return val ? val : c;
+ {
+ /* Not all uppercase letters are guaranteed to have a lowercase
+ * equivalent. If this is the case, val will be zero. */
+ return val ? val : c;
+ }
}
else if (t == G_UNICODE_TITLECASE_LETTER)
{
for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
{
if (title_table[i][0] == c)
- val = title_table[i][1];
+ {
+ val = title_table[i][1];
+ break;
+ }
}
}
- len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
+ /* Some lowercase letters, e.g., U+000AA, FEMININE ORDINAL INDICATOR,
+ * do not have an uppercase equivalent, in which case val will be
+ * zero. */
+ len += g_unichar_to_utf8 (val ? val : c, out_buffer ? out_buffer + len : NULL);
}
}
else
for (i = 0; i < G_N_ELEMENTS (title_table); ++i)
{
if (title_table[i][0] == c)
- val = title_table[i][2];
+ {
+ val = title_table[i][2];
+ break;
+ }
}
}
- len += g_unichar_to_utf8 (val, out_buffer ? out_buffer + len : NULL);
+ /* Not all uppercase letters are guaranteed to have a lowercase
+ * equivalent. If this is the case, val will be zero. */
+ len += g_unichar_to_utf8 (val ? val : c, out_buffer ? out_buffer + len : NULL);
}
}
else
}
+#define G_SCRIPT_TABLE_MIDPOINT (G_N_ELEMENTS (g_script_table) / 2)
+
+static inline GUnicodeScript
+g_unichar_get_script_bsearch (gunichar ch)
+{
+ int lower = 0;
+ int upper = G_N_ELEMENTS (g_script_table) - 1;
+ static int saved_mid = G_SCRIPT_TABLE_MIDPOINT;
+ int mid = saved_mid;
+
+
+ do
+ {
+ if (ch < g_script_table[mid].start)
+ upper = mid - 1;
+ else if (ch >= g_script_table[mid].start + g_script_table[mid].chars)
+ lower = mid + 1;
+ else
+ return g_script_table[saved_mid = mid].script;
+
+ mid = (lower + upper) / 2;
+ }
+ while (lower <= upper);
+
+ return G_UNICODE_SCRIPT_UNKNOWN;
+}
+
+/**
+ * g_unichar_get_script:
+ * @ch: a Unicode character
+ *
+ * Looks up the #GUnicodeScript for a particular character (as defined
+ * by Unicode Standard Annex #24). No check is made for @ch being a
+ * valid Unicode character; if you pass in invalid character, the
+ * result is undefined.
+ *
+ * Return value: the #GUnicodeScript for the character.
+ *
+ * Since: 2.14
+ */
+GUnicodeScript
+g_unichar_get_script (gunichar ch)
+{
+ if (ch < G_EASY_SCRIPTS_RANGE)
+ return g_script_easy_table[ch];
+ else
+ return g_unichar_get_script_bsearch (ch);
+}
+
+
#define __G_UNIPROP_C__
#include "galiasdef.c"
projects / platform / upstream / glib.git / blobdiff